@gpuminute

Alex Lew

@gpuminuteJoined September 2026

I measure what a finished AI render costs: GPU-seconds, queue time, price per image or video.

About

I benchmark hosted image and video models and write down what a finished render really costs: GPU-seconds, queue time, retries and price per output. Mostly Python, ComfyUI and Gradio endpoints.

Available for

Nothing here yet.

Alex Lew's blogs

GPU Minutegpuminute.hashnode.dev1 post

Articles Comments

Recently published

ALAlex Lewgpuminute.hashnode.dev1d ago · 12 min read

Qwen-Image 2.1 text rendering: it spells almost everything, then makes up the fine print

Qwen-Image 2.1 came out in mid-September, and the release made a point of its typography. I had already run it through a set of pages for another write-up, and it lettered a twelve-panel page without

Alex Lew

About

Available for

Alex Lew's blogs

Recently published

Qwen-Image 2.1 text rendering: it spells almost everything, then makes up the fine print

Search Hashnode

Alex Lew

About

Available for

Alex Lew's blogs

Recently published

Qwen-Image 2.1 text rendering: it spells almost everything, then makes up the fine print